gpt-image-2-ecommerce-main-image

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The runtime path cmd_image()/client.generate_image() ingests outsider-supplied --prompt (free text) into the POST body as prompt for openapi/v1/generation/image, so an outsider can supply poison directly to the workflow.